Machine Learning and Time Series Approaches for Stock Price Prediction: A Case Study of Indian Banks

The Finance sector plays an important role in the economy of any country. With increased recognition of the stock market and its importance in the economy, correct investments and portfolio management has been the top priority in this sector. With the introduction of machine learning and time series models this has been easier. This research paper focuses on the comparative analysis of three most used machine learning and time series models namely Autoregressive Integrated Moving Average (ARIMA), Seasonal Autoregressive Integrated Moving Average (SARIMA) and Long Term Short Term Memory (LSTM) in predicting the stock prices of the Indian Banks namely ICICI Bank, IndusInd Bank, State Bank Of India, Kotak Mahindra Bank, HDFC Bank and Axis Bank using efficient and time saving means. Each models’ accuracy is evaluated using error metrics like Root Mean Square Error, Mean Squared Error and Mean Absolute Error. The findings aim to provide an insight about the most preferred model in this field and also help financial analysts and investors to make the correct decisions while investing into the market.